News for hackers. Stuff that matters.
Re:Google has developed speech-recognition technology that a... by IDisposableHero on Friday April 08, 2011 @11:59AM (#2424339)
It got "how much wood would a woodchuck chuck if a wouldchuck would chuck wood" right for me. I am impressed now.

But it couldn't handle "Ph'nglui mglw'nafh Cthulhu R'lyeh wgah'nagl fhtagn" Maybe I'm not pronouncing it quite right.

Re:Google has developed speech-recognition technology that a... by ppod on Friday April 08, 2011 @05:44PM (#2425718)
"how much wood would a woodchuck chuck if a wouldchuck would chuck wood"

That isn't really the best example, considering how these systems tend to work. If their system has a giant bank of text it's using to predict the statistical likelihood of your next word, once you've said "how much wood ..", 'would' is a very high probability candidate for the next word, and once you get to 'woodchuck' the rest is statistically almost inevitable.

A better 'difficult' test would be something along the lines of 'colorless green ideas sleep furiously', although we can't actually use that one since that example is so famous it would likely turn up in a web-derived corpus many times.

Re:Google has developed speech-recognition technology that a... by Cyndre on Saturday April 09, 2011 @03:09AM (#2426695)
How is that even a test for it? If you input garbage into a system like that your going to get garbage out. And for fun, walk up to a stranger and say something like that and see if the stranger can provide useful information.
Re:Google has developed speech-recognition technology that a... by IDisposableHero on Monday April 11, 2011 @08:54AM (#2432374)
Yes, it kind of failed on "movie times for 'source code'". That's a sentence that's hard to parse without context ;)
Re:Google has developed speech-recognition technology that a... by StavrosK on Friday April 08, 2011 @12:02PM (#2424356)
Are you sure you pronounced all the schwas?